patrickvonplaten commited on
Commit
f584132
·
verified ·
1 Parent(s): cc3167a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -2
README.md CHANGED
@@ -4,8 +4,8 @@ license: apache-2.0
4
 
5
  # Model Card for Mathstral-7B-v0.1
6
 
7
- <Fill-me for Mathstral-7B-v0.1>
8
  Mathstral 7B is a model specializing in mathematical and scientific tasks, based on Mistral 7B.
 
9
 
10
  ## Installation
11
 
@@ -34,9 +34,14 @@ snapshot_download(repo_id="mistralai/mathstral-7B-v0.1", allow_patterns=["params
34
  After installing `mistral_inference`, a `mistral-demo` CLI command should be available in your environment.
35
 
36
  ```
37
- mistral-chat $HOME/mistral_models/mathstral-7B-v0.1 --instruct
38
  ```
39
 
 
 
 
 
 
40
 
41
  ## Evaluation
42
  We evaluate Mathstral 7B and open-weight models of the similar size on industry-standard benchmarks.
 
4
 
5
  # Model Card for Mathstral-7B-v0.1
6
 
 
7
  Mathstral 7B is a model specializing in mathematical and scientific tasks, based on Mistral 7B.
8
+ You can read more in the [official blog post](https://mistral.ai/news/mathstral/).
9
 
10
  ## Installation
11
 
 
34
  After installing `mistral_inference`, a `mistral-demo` CLI command should be available in your environment.
35
 
36
  ```
37
+ mistral-chat $HOME/mistral_models/mathstral-7B-v0.1 --instruct --max_tokens 256
38
  ```
39
 
40
+ You can then start chatting with the model, *e.g.* prompt it with something like:
41
+
42
+ ```
43
+ "Albert likes to surf every week. Each surfing session lasts for 4 hours and costs $20 per hour. How much would Albert spend in 5 weeks?"
44
+ ```
45
 
46
  ## Evaluation
47
  We evaluate Mathstral 7B and open-weight models of the similar size on industry-standard benchmarks.